Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912994694266880 |
|---|---|
| author | Bouzidi, Halima Liu, Haoyu Achamyeleh, Yonatan Gizachew Iddamsetty, Praneetsai Vasu Faruque, Mohammad Abdullah Al |
| author_facet | Bouzidi, Halima Liu, Haoyu Achamyeleh, Yonatan Gizachew Iddamsetty, Praneetsai Vasu Faruque, Mohammad Abdullah Al |
| contents | Recent Tracking-by-Query-Propagation (TBP) methods have advanced Multi-Object Tracking (MOT) by enabling end-to-end (E2E) pipelines with long-range temporal modeling. However, this reliance on query propagation introduces unexplored architectural vulnerabilities to adversarial attacks. We present FADE, a novel attack framework designed to exploit these specific vulnerabilities. FADE employs two attack strategies targeting core TBP mechanisms: (i) Temporal Query Flooding: Generates spurious temporally consistent track queries to exhaust the tracker's limited query budget, forcing it to terminate valid tracks. (ii) Temporal Memory Corruption: Directly attacks the query updater's memory by severing temporal links via state de-correlation and erasing the learned feature identity of matched tracks. Furthermore, we introduce a differentiable pipeline to optimize these attacks for physical-world realizability by leveraging simulations of advanced perception sensor spoofing. Experiments on MOT17 and MOT20 benchmarks demonstrate that FADE is highly effective against state-of-the-art TBP trackers, causing significant identity switches and track terminations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00452 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation Bouzidi, Halima Liu, Haoyu Achamyeleh, Yonatan Gizachew Iddamsetty, Praneetsai Vasu Faruque, Mohammad Abdullah Al Computer Vision and Pattern Recognition Recent Tracking-by-Query-Propagation (TBP) methods have advanced Multi-Object Tracking (MOT) by enabling end-to-end (E2E) pipelines with long-range temporal modeling. However, this reliance on query propagation introduces unexplored architectural vulnerabilities to adversarial attacks. We present FADE, a novel attack framework designed to exploit these specific vulnerabilities. FADE employs two attack strategies targeting core TBP mechanisms: (i) Temporal Query Flooding: Generates spurious temporally consistent track queries to exhaust the tracker's limited query budget, forcing it to terminate valid tracks. (ii) Temporal Memory Corruption: Directly attacks the query updater's memory by severing temporal links via state de-correlation and erasing the learned feature identity of matched tracks. Furthermore, we introduce a differentiable pipeline to optimize these attacks for physical-world realizability by leveraging simulations of advanced perception sensor spoofing. Experiments on MOT17 and MOT20 benchmarks demonstrate that FADE is highly effective against state-of-the-art TBP trackers, causing significant identity switches and track terminations. |
| title | Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00452 |